VIBE (MiniMax) - Web: leaderboard
The Web subset of MiniMax's VIBE: the model, run by MiniMax, builds front-end web apps from a written requirement, and a vision-capable verifier agent scores the running result, averaged over three runs. MiniMax does not say how many tasks each model ran; the released set has 40 Web prompts.
Metric: Score (0-100). Source: github.com. Saturation forecast: Estimated already saturated. 5 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | MiniMax-M2.1 | 91.5 | #573 |
| 2 | Gemini 3 Pro | 89.5 | #145 |
| 3 | Claude Opus 4.5 | 89.1 | #161 |
| 4 | Claude Sonnet 4.5 | 87.3 | #258 |
| 5 | MiniMax-M2 | 80.4 | #687 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=vibe-minimax-web · How It Works · Data refreshed daily, snapshot 2026-11-17.